Robust 6G Network Localization via HWKNN Regression and Conditional GAN Data Synthesis

With the rapid advancement of wireless communication technologies and the growing demand for accurate location-based services, the localization accuracy of mobile devices in 6G networks has become increasingly important. Existing single-feature fingerprint localization methods face several limitations, such as susceptibility to multipath effects, non-line-of-sight propagation, and the complexity of diverse environments. To address these challenges, this paper proposes a novel multi-feature hierarchical weighted K-Nearest Neighbor (HWKNN) regression algorithm for 6G localization, leveraging base station data. This method optimizes the Weighted K-Nearest Neighbor (WKNN) algorithm by assigning different weights to multiple signal features, improving robustness and accuracy. In addition to signal data limitations caused by sparse and expensive field measurements, this research introduces a Conditional Generative Adversarial Network (CGAN) to generate synthetic fingerprint data, incorporating base station coordinates as conditional inputs. Experimental results demonstrate that using CGAN-generated data reduces localization error from 31m to 15m, showcasing the method's superior performance. The key findings of the study include that multi-feature localization significantly enhances robustness compared to single-feature methods, the HWKNN algorithm effectively adapts to signal fluctuations by assigning feature-specific weights, and the integration of CGAN-generated data improves localization accuracy while reducing the need for extensive field data collection. This research makes a significant contribution to 6G localization by combining advanced machine learning techniques with optimized fingerprint localization methods, offering both practical and engineering value for future networks.